Learning Entity and Relation Embeddings with Entity Description for Knowledge Graph Completion

Abstract

With the growth of existing knowledge graph, the completion of knowledge graph has become a crucial problem. In this paper, we propose a novel model based on descriptionembodied knowledge representation learning framework, which is able to take advantages of both fact triples and entity description. Specifically, the relation projection is combined with description-embodied representation learning to learn entity and relation embeddings. Convolutional neural network and TransR are adopted to get the description-based and structure-based representation of entity and relation, respectively. We employ FB15K dataset generated from a large knowledge graph freebase, to evaluate the performances of the proposed model. Experimental results show that our proposed model greatly outperforms other existing baseline models.